Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 121092
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    リ
    -0.07
    以
    -0.07
     meetings
    -0.07
    rey
    -0.06
     pane
    -0.06
     SPA
    -0.06
     conditions
    -0.06
     Lawrence
    -0.06
     repo
    -0.06
    //:
    -0.06
    POSITIVE LOGITS
     ><?
    0.07
     downstairs
    0.07
    äsent
    0.06
    )↵↵↵↵
    0.06
    _valor
    0.06
    ่าม
    0.06
     جلو
    0.06
    <pcl
    0.06
     użytk
    0.06
    MYSQL
    0.06
    Activations Density 0.004%

    No Known Activations